Fast spark discharge-laser-induced breakdown spectroscopy method for rice botanic origin determination

Abstract

A simple, fast, and efficient spark discharge-laser-induced breakdown spectroscopy (SD-LIBS) method was developed for determining rice botanic origin using predictive modeling based on support vector machine (SVM).Seventy-two samples from four rice varieties (Guri, Irga 424, Puitá, and Taim) were analyzed by SD-LIBS.Spectral lines of C, Ca, Fe, Mg, N and Na were selected as input variables for prediction model fitting. The SVMalgorithm parameters were optimized using a central composite design (CCD) to find the better classificationperformance. The optimum model for discriminating rice samples according to their botanical variety was obtained using C = 5.25 and γ = 0.119. This model achieved 96.4% of correct predictions in test samples andshowed sensitivities and specificities per class within the range of 92?100%. The developed method is robust andeco-friendly for rice botanic identification since its prediction results are consistent and reproducible and itsapplication does not generate chemical waste.